Accelerating diagnosis of Parkinson’s disease through risk prediction
Abstract Background Characterization of prediagnostic Parkinson’s Disease (PD) and early prediction of subsequent development are critical for preventive interventions, risk stratification and understanding of disease pathology. This study aims to characterize the role of the prediagnostic period in...
Main Authors: | , , , , , , , , , , , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
BMC
2021-05-01
|
Series: | BMC Neurology |
Subjects: | |
Online Access: | https://doi.org/10.1186/s12883-021-02226-4 |
id |
doaj-9e6364d125584b15943a54481769b978 |
---|---|
record_format |
Article |
spelling |
doaj-9e6364d125584b15943a54481769b9782021-05-23T11:25:37ZengBMCBMC Neurology1471-23772021-05-0121111210.1186/s12883-021-02226-4Accelerating diagnosis of Parkinson’s disease through risk predictionWilliam Yuan0Brett Beaulieu-Jones1Richard Krolewski2Nathan Palmer3Christine Veyrat-Follet4Francesca Frau5Caroline Cohen6Sylvie Bozzi7Meaghan Cogswell8Dinesh Kumar9Catherine Coulouvrat10Bruno Leroy11Tanya Z. Fischer12S. Pablo Sardi13Karen J. Chandross14Lee L. Rubin15Anne-Marie Wills16Isaac Kohane17Scott L. Lipnick18Department of Biomedical Informatics, Harvard Medical SchoolDepartment of Biomedical Informatics, Harvard Medical SchoolDepartment of Stem Cell and Regenerative Biology, Harvard UniversityDepartment of Biomedical Informatics, Harvard Medical SchoolSanofiSanofi-Aventis Deutschland GmbHSanofiSanofiSanofiSanofiSanofiSanofiSanofiSanofiSanofi R&D, 55 Corporate DriveDepartment of Stem Cell and Regenerative Biology, Harvard UniversityNeurological Clinical Research Institute (NCRI), Massachusetts General Hospital (MGH)Department of Biomedical Informatics, Harvard Medical SchoolDepartment of Biomedical Informatics, Harvard Medical SchoolAbstract Background Characterization of prediagnostic Parkinson’s Disease (PD) and early prediction of subsequent development are critical for preventive interventions, risk stratification and understanding of disease pathology. This study aims to characterize the role of the prediagnostic period in PD and, using selected features from this period as novel interception points, construct a prediction model to accelerate the diagnosis in a real-world setting. Methods We constructed two sets of machine learning models: a retrospective approach highlighting exposures up to 5 years prior to PD diagnosis, and an alternative model that prospectively predicted future PD diagnosis from all individuals at their first diagnosis of a gait or tremor disorder, these being features that appeared to represent the initiation of a differential diagnostic window. Results We found many novel features captured by the retrospective models; however, the high accuracy was primarily driven from surrogate diagnoses for PD, such as gait and tremor disorders, suggesting the presence of a distinctive differential diagnostic period when the clinician already suspected PD. The model utilizing a gait/tremor diagnosis as the interception point, achieved a validation AUC of 0.874 with potential time compression to a future PD diagnosis of more than 300 days. Comparisons of predictive diagnoses between the prospective and prediagnostic cohorts suggest the presence of distinctive trajectories of PD progression based on comorbidity profiles. Conclusions Overall, our machine learning approach allows for both guiding clinical decisions such as the initiation of neuroprotective interventions and importantly, the possibility of earlier diagnosis for clinical trials for disease modifying therapies.https://doi.org/10.1186/s12883-021-02226-4Parkinson’s diseasePredictive medicineProdromalPrediagnosticTremorGait |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
William Yuan Brett Beaulieu-Jones Richard Krolewski Nathan Palmer Christine Veyrat-Follet Francesca Frau Caroline Cohen Sylvie Bozzi Meaghan Cogswell Dinesh Kumar Catherine Coulouvrat Bruno Leroy Tanya Z. Fischer S. Pablo Sardi Karen J. Chandross Lee L. Rubin Anne-Marie Wills Isaac Kohane Scott L. Lipnick |
spellingShingle |
William Yuan Brett Beaulieu-Jones Richard Krolewski Nathan Palmer Christine Veyrat-Follet Francesca Frau Caroline Cohen Sylvie Bozzi Meaghan Cogswell Dinesh Kumar Catherine Coulouvrat Bruno Leroy Tanya Z. Fischer S. Pablo Sardi Karen J. Chandross Lee L. Rubin Anne-Marie Wills Isaac Kohane Scott L. Lipnick Accelerating diagnosis of Parkinson’s disease through risk prediction BMC Neurology Parkinson’s disease Predictive medicine Prodromal Prediagnostic Tremor Gait |
author_facet |
William Yuan Brett Beaulieu-Jones Richard Krolewski Nathan Palmer Christine Veyrat-Follet Francesca Frau Caroline Cohen Sylvie Bozzi Meaghan Cogswell Dinesh Kumar Catherine Coulouvrat Bruno Leroy Tanya Z. Fischer S. Pablo Sardi Karen J. Chandross Lee L. Rubin Anne-Marie Wills Isaac Kohane Scott L. Lipnick |
author_sort |
William Yuan |
title |
Accelerating diagnosis of Parkinson’s disease through risk prediction |
title_short |
Accelerating diagnosis of Parkinson’s disease through risk prediction |
title_full |
Accelerating diagnosis of Parkinson’s disease through risk prediction |
title_fullStr |
Accelerating diagnosis of Parkinson’s disease through risk prediction |
title_full_unstemmed |
Accelerating diagnosis of Parkinson’s disease through risk prediction |
title_sort |
accelerating diagnosis of parkinson’s disease through risk prediction |
publisher |
BMC |
series |
BMC Neurology |
issn |
1471-2377 |
publishDate |
2021-05-01 |
description |
Abstract Background Characterization of prediagnostic Parkinson’s Disease (PD) and early prediction of subsequent development are critical for preventive interventions, risk stratification and understanding of disease pathology. This study aims to characterize the role of the prediagnostic period in PD and, using selected features from this period as novel interception points, construct a prediction model to accelerate the diagnosis in a real-world setting. Methods We constructed two sets of machine learning models: a retrospective approach highlighting exposures up to 5 years prior to PD diagnosis, and an alternative model that prospectively predicted future PD diagnosis from all individuals at their first diagnosis of a gait or tremor disorder, these being features that appeared to represent the initiation of a differential diagnostic window. Results We found many novel features captured by the retrospective models; however, the high accuracy was primarily driven from surrogate diagnoses for PD, such as gait and tremor disorders, suggesting the presence of a distinctive differential diagnostic period when the clinician already suspected PD. The model utilizing a gait/tremor diagnosis as the interception point, achieved a validation AUC of 0.874 with potential time compression to a future PD diagnosis of more than 300 days. Comparisons of predictive diagnoses between the prospective and prediagnostic cohorts suggest the presence of distinctive trajectories of PD progression based on comorbidity profiles. Conclusions Overall, our machine learning approach allows for both guiding clinical decisions such as the initiation of neuroprotective interventions and importantly, the possibility of earlier diagnosis for clinical trials for disease modifying therapies. |
topic |
Parkinson’s disease Predictive medicine Prodromal Prediagnostic Tremor Gait |
url |
https://doi.org/10.1186/s12883-021-02226-4 |
work_keys_str_mv |
AT williamyuan acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT brettbeaulieujones acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT richardkrolewski acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT nathanpalmer acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT christineveyratfollet acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT francescafrau acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT carolinecohen acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT sylviebozzi acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT meaghancogswell acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT dineshkumar acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT catherinecoulouvrat acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT brunoleroy acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT tanyazfischer acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT spablosardi acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT karenjchandross acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT leelrubin acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT annemariewills acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT isaackohane acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction AT scottllipnick acceleratingdiagnosisofparkinsonsdiseasethroughriskprediction |
_version_ |
1721429714901401600 |